Chapter 8 HMSC analysis
8.2 Variance partitioning
# Compute variance partitioning
varpart=computeVariancePartitioning(m)
varpart$vals %>%
as.data.frame() %>%
rownames_to_column(var="variable") %>%
pivot_longer(!variable, names_to = "genome", values_to = "value") %>%
mutate(variable=factor(variable, levels=rev(c("origin","sex","logseqdepth","Random: location")))) %>%
group_by(variable) %>%
summarise(mean=mean(value)*100,sd=sd(value)*100) %>%
tt()| variable | mean | sd |
|---|---|---|
| Random: location | 37.900015 | 25.317903 |
| logseqdepth | 56.110626 | 25.796874 |
| sex | 4.937460 | 5.612719 |
| origin | 1.051899 | 1.282563 |
# Basal tree
varpart_tree <- genome_tree
#Varpart table
varpart_table <- varpart$vals %>%
as.data.frame() %>%
rownames_to_column(var="variable") %>%
pivot_longer(!variable, names_to = "genome", values_to = "value") %>%
mutate(genome=factor(genome, levels=rev(varpart_tree$tip.label))) %>%
mutate(variable=factor(variable, levels=rev(c("origin","sex","logseqdepth","Random: location"))))
#Phylums
phylum_colors <- read_tsv("https://raw.githubusercontent.com/earthhologenome/EHI_taxonomy_colour/main/ehi_phylum_colors.tsv") %>%
right_join(genome_metadata, by=join_by(phylum == phylum)) %>%
filter(genome %in% varpart_tree$tip.label) %>%
arrange(match(genome, varpart_tree$tip.label)) %>%
mutate(phylum = factor(phylum, levels = unique(phylum))) %>%
column_to_rownames(var = "genome") %>%
select(phylum)
colors_alphabetic <- read_tsv("https://raw.githubusercontent.com/earthhologenome/EHI_taxonomy_colour/main/ehi_phylum_colors.tsv") %>%
right_join(genome_metadata, by=join_by(phylum == phylum)) %>%
filter(genome %in% varpart_tree$tip.label) %>%
arrange(match(genome, varpart_tree$tip.label)) %>%
select(phylum, colors) %>%
unique() %>%
arrange(phylum) %>%
select(colors) %>%
pull()
# Basal ggtree
varpart_tree <- varpart_tree %>%
force.ultrametric(.,method="extend") %>%
ggtree(., size = 0.3)***************************************************************
* Note: *
* force.ultrametric does not include a formal method to *
* ultrametricize a tree & should only be used to coerce *
* a phylogeny that fails is.ultrametric due to rounding -- *
* not as a substitute for formal rate-smoothing methods. *
***************************************************************
# Add phylum colors next to the tree tips
varpart_tree <- gheatmap(varpart_tree, phylum_colors, offset=-0.2, width=0.1, colnames=FALSE) +
scale_fill_manual(values=colors_alphabetic)+
labs(fill="Phylum")
#Reset fill scale to use a different colour profile in the heatmap
varpart_tree <- varpart_tree + new_scale_fill()
# Add variance stacked barplot
vertical_tree <- varpart_tree +
scale_fill_manual(values=c("#506a96","#cccccc","#be3e2b","#f6de6c"))+
geom_fruit(
data=varpart_table,
geom=geom_bar,
mapping = aes(x=value, y=genome, fill=variable, group=variable),
pwidth = 2,
offset = 0.05,
width= 1,
orientation="y",
stat="identity")+
labs(fill="Variable")
vertical_tree8.3 Posterior estimates
# Select desired support threshold
support=0.9
negsupport=1-support
# Basal tree
postestimates_tree <- genome_tree
# Posterior estimate table
post_beta <- getPostEstimate(hM=m, parName="Beta")$support %>%
as.data.frame() %>%
mutate(variable=m$covNames) %>%
pivot_longer(!variable, names_to = "genome", values_to = "value") %>%
mutate(genome=factor(genome, levels=rev(postestimates_tree$tip.label))) %>%
mutate(value = case_when(
value >= support ~ "Positive",
value <= negsupport ~ "Negative",
TRUE ~ "Neutral")) %>%
mutate(value=factor(value, levels=c("Positive","Neutral","Negative"))) %>%
pivot_wider(names_from = variable, values_from = value) %>%
#select(genome,sp_vulgaris,area_semi,area_urban,sp_vulgarisxarea_semi,sp_vulgarisxarea_urban,season_spring,season_winter,sp_vulgarisxseason_spring,sp_vulgarisxseason_winter) %>%
column_to_rownames(var="genome")
#Phylums
phylum_colors <- read_tsv("https://raw.githubusercontent.com/earthhologenome/EHI_taxonomy_colour/main/ehi_phylum_colors.tsv") %>%
mutate(phylum=str_remove_all(phylum, "p__")) %>%
right_join(genome_metadata, by=join_by(phylum == phylum)) %>%
filter(genome %in% postestimates_tree$tip.label) %>%
arrange(match(genome, postestimates_tree$tip.label)) %>%
mutate(phylum = factor(phylum, levels = unique(phylum))) %>%
column_to_rownames(var = "genome") %>%
select(phylum)
colors_alphabetic <- read_tsv("https://raw.githubusercontent.com/earthhologenome/EHI_taxonomy_colour/main/ehi_phylum_colors.tsv") %>%
mutate(phylum=str_remove_all(phylum, "p__")) %>%
right_join(genome_metadata, by=join_by(phylum == phylum)) %>%
filter(genome %in% postestimates_tree$tip.label) %>%
arrange(match(genome, postestimates_tree$tip.label)) %>%
select(phylum, colors) %>%
unique() %>%
arrange(phylum) %>%
select(colors) %>%
pull()
# Basal ggtree
postestimates_tree <- postestimates_tree %>%
force.ultrametric(.,method="extend") %>%
ggtree(., size = 0.3)***************************************************************
* Note: *
* force.ultrametric does not include a formal method to *
* ultrametricize a tree & should only be used to coerce *
* a phylogeny that fails is.ultrametric due to rounding -- *
* not as a substitute for formal rate-smoothing methods. *
***************************************************************
#Add phylum colors next to the tree tips
postestimates_tree <- gheatmap(postestimates_tree, phylum_colors, offset=-0.2, width=0.1, colnames=FALSE) +
scale_fill_manual(values=colors_alphabetic)+
labs(fill="Phylum")
#Reset fill scale to use a different colour profile in the heatmap
postestimates_tree <- postestimates_tree + new_scale_fill()
# Add posterior significant heatmap
postestimates_tree <- gheatmap(postestimates_tree, post_beta, offset=0, width=0.5, colnames=TRUE, colnames_position="top",colnames_angle=90, colnames_offset_y=1, hjust=0) +
scale_fill_manual(values=c("#be3e2b","#f4f4f4","#b2b530"))+
labs(fill="Trend")
postestimates_tree +
vexpand(.25, 1) # expand top
## Correlations
#Compute the residual correlation matrix
OmegaCor = computeAssociations(m)
# Refernece tree (for sorting genomes)
genome_tree_subset <- genome_tree %>%
keep.tip(., tip=m$spNames)
#Co-occurrence matrix at the animal level
supportLevel = 0.95
toPlot = ((OmegaCor[[1]]$support>supportLevel)
+ (OmegaCor[[1]]$support<(1-supportLevel))>0)*OmegaCor[[1]]$mean
matrix <- toPlot %>%
as.data.frame() %>%
rownames_to_column(var="genome1") %>%
pivot_longer(!genome1, names_to = "genome2", values_to = "cor") %>%
mutate(genome1= factor(genome1, levels=genome_tree_subset$tip.label)) %>%
mutate(genome2= factor(genome2, levels=genome_tree_subset$tip.label)) %>%
ggplot(aes(x = genome1, y = genome2, fill = cor)) +
geom_tile() +
scale_fill_gradient2(low = "#be3e2b",
mid = "#f4f4f4",
high = "#b2b530")+
theme_void()
htree <- genome_tree_subset %>%
force.ultrametric(.,method="extend") %>%
ggtree(.)***************************************************************
* Note: *
* force.ultrametric does not include a formal method to *
* ultrametricize a tree & should only be used to coerce *
* a phylogeny that fails is.ultrametric due to rounding -- *
* not as a substitute for formal rate-smoothing methods. *
***************************************************************
***************************************************************
* Note: *
* force.ultrametric does not include a formal method to *
* ultrametricize a tree & should only be used to coerce *
* a phylogeny that fails is.ultrametric due to rounding -- *
* not as a substitute for formal rate-smoothing methods. *
***************************************************************
#create composite figure
grid.arrange(grobs = list(matrix,vtree),
layout_matrix = rbind(c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1),
c(2,1,1,1,1,1,1,1,1,1,1,1)))8.4 Predict responses
# Select modelchain of interest
load("hmsc/fit_model1_250_10.Rdata")
gradient = c("domestic","feral")
gradientlength = length(gradient)
#Treatment-specific gradient predictions
pred <- constructGradient(m,
focalVariable = "origin",
non.focalVariables = list(logseqdepth=list(1),location=list(1))) %>%
predict(m, Gradient = ., expected = TRUE) %>%
do.call(rbind,.) %>%
as.data.frame() %>%
mutate(origin=rep(gradient,1000)) %>%
pivot_longer(!origin,names_to = "genome", values_to = "value")# weights: 9 (4 variable)
initial value 101.072331
final value 91.392443
converged
8.4.0.1 Function level
functions_table <- elements_table %>%
to.functions(., GIFT_db) %>%
as.data.frame()
community_functions <- pred %>%
group_by(origin, genome) %>%
mutate(row_id = row_number()) %>%
pivot_wider(names_from = genome, values_from = value) %>%
ungroup() %>%
group_split(row_id) %>%
as.list() %>%
lapply(., FUN = function(x){x %>%
select(-row_id) %>%
column_to_rownames(var = "origin") %>%
as.data.frame() %>%
exp() %>%
t() %>%
tss() %>%
to.community(functions_table,.,GIFT_db) %>%
as.data.frame() %>%
rownames_to_column(var="origin")
})#max-min option
calculate_slope <- function(x) {
lm_fit <- lm(unlist(x) ~ seq_along(unlist(x)))
coef(lm_fit)[2]
}
function_predictions <- map_dfc(community_functions, function(mat) {
mat %>%
column_to_rownames(var = "origin") %>%
t() %>%
as.data.frame() %>%
rowwise() %>%
mutate(slope = calculate_slope(c_across(everything()))) %>%
select(slope) }) %>%
t() %>%
as.data.frame() %>%
set_names(colnames(community_functions[[1]])[-1]) %>%
rownames_to_column(var="iteration") %>%
pivot_longer(!iteration, names_to="trait",values_to="value") %>%
group_by(trait) %>%
summarise(mean=mean(value),
p1 = quantile(value, probs = 0.1),
p9 = quantile(value, probs = 0.9),
positive_support = sum(value > 0)/1000,
negative_support = sum(value < 0)/1000) %>%
arrange(-positive_support)
# Positively associated
function_predictions %>%
filter(mean >0) %>%
arrange(-positive_support) %>%
tt()| trait | mean | p1 | p9 | positive_support | negative_support |
|---|---|---|---|---|---|
| D02 | 7.943818e-03 | -0.0035659330 | 0.0203998706 | 0.814 | 0.186 |
| B08 | 8.140762e-03 | -0.0035118978 | 0.0196807401 | 0.787 | 0.213 |
| B01 | 9.817798e-04 | -0.0056385892 | 0.0083570721 | 0.632 | 0.368 |
| S01 | 5.721836e-04 | -0.0126077833 | 0.0130786482 | 0.565 | 0.435 |
| B10 | 1.741428e-06 | -0.0002973356 | 0.0002604708 | 0.486 | 0.514 |
# Negatively associated
function_predictions %>%
filter(mean <0) %>%
arrange(-negative_support) %>%
tt()| trait | mean | p1 | p9 | positive_support | negative_support |
|---|---|---|---|---|---|
| D08 | -1.214862e-03 | -0.0022939461 | -1.937513e-04 | 0.051 | 0.949 |
| B03 | -1.055852e-02 | -0.0180263536 | -2.778997e-03 | 0.055 | 0.945 |
| D06 | -3.137025e-03 | -0.0067440893 | 2.240275e-05 | 0.101 | 0.899 |
| B04 | -8.879801e-03 | -0.0199137473 | 7.496508e-04 | 0.128 | 0.872 |
| B06 | -7.017554e-03 | -0.0175214946 | 2.467422e-03 | 0.178 | 0.822 |
| D07 | -1.232191e-02 | -0.0308839790 | 4.181036e-03 | 0.181 | 0.819 |
| D03 | -4.200875e-03 | -0.0132245471 | 3.655181e-03 | 0.213 | 0.787 |
| D05 | -1.360651e-03 | -0.0074006070 | 4.341303e-03 | 0.241 | 0.759 |
| S03 | -9.012202e-03 | -0.0328886683 | 1.716974e-02 | 0.271 | 0.729 |
| B02 | -3.478904e-03 | -0.0124916077 | 5.407998e-03 | 0.284 | 0.716 |
| S02 | -5.147206e-03 | -0.0156994292 | 2.781468e-03 | 0.302 | 0.698 |
| B07 | -3.782134e-03 | -0.0165121548 | 9.410750e-03 | 0.330 | 0.670 |
| D09 | -1.847566e-03 | -0.0086808845 | 5.390441e-03 | 0.330 | 0.670 |
| B09 | -2.027127e-05 | -0.0005793415 | 4.283062e-04 | 0.366 | 0.634 |
| D01 | -2.273005e-04 | -0.0052248355 | 4.232479e-03 | 0.436 | 0.564 |
positive <- function_predictions %>%
filter(mean >0) %>%
arrange(mean) %>%
filter(positive_support>=0.9) %>%
select(-negative_support) %>%
rename(support=positive_support)
negative <- function_predictions %>%
filter(mean <0) %>%
arrange(mean) %>%
filter(negative_support>=0.9) %>%
select(-positive_support) %>%
rename(support=negative_support)
bind_rows(positive,negative) %>%
left_join(GIFT_db,by=join_by(trait==Code_function)) %>%
mutate(trait=factor(trait,levels=c(rev(positive$trait),rev(negative$trait)))) %>%
ggplot(aes(x=mean, y=fct_rev(trait), xmin=p1, xmax=p9, color=Function)) +
geom_point() +
geom_errorbar() +
xlim(c(-0.02,0.02)) +
geom_vline(xintercept=0) +
scale_color_manual(values = c("#debc14","#440526","#dc7c17","#172742","#debc14","#440526","#dc7c17","#172742","#357379","#6c7e2c","#d8dc69","#774d35","#db717d")) +
theme_minimal() +
labs(x="Regression coefficient",y="Functional trait")8.4.0.2 Element level
elements_table <- genome_gifts %>%
to.elements(., GIFT_db) %>%
as.data.frame()
community_elements <- pred %>%
group_by(origin, genome) %>%
mutate(row_id = row_number()) %>%
pivot_wider(names_from = genome, values_from = value) %>%
ungroup() %>%
group_split(row_id) %>%
as.list() %>%
lapply(., FUN = function(x){x %>%
select(-row_id) %>%
column_to_rownames(var = "origin") %>%
as.data.frame() %>%
exp() %>%
t() %>%
tss() %>%
to.community(elements_table,.,GIFT_db) %>%
as.data.frame() %>%
rownames_to_column(var="origin")
})
calculate_slope <- function(x) {
lm_fit <- lm(unlist(x) ~ seq_along(unlist(x)))
coef(lm_fit)[2]
}
element_predictions <- map_dfc(community_elements, function(mat) {
mat %>%
column_to_rownames(var = "origin") %>%
t() %>%
as.data.frame() %>%
rowwise() %>%
mutate(slope = calculate_slope(c_across(everything()))) %>%
select(slope) }) %>%
t() %>%
as.data.frame() %>%
set_names(colnames(community_elements[[1]])[-1]) %>%
rownames_to_column(var="iteration") %>%
pivot_longer(!iteration, names_to="trait",values_to="value") %>%
group_by(trait) %>%
summarise(mean=mean(value),
p1 = quantile(value, probs = 0.1),
p9 = quantile(value, probs = 0.9),
positive_support = sum(value > 0)/1000,
negative_support = sum(value < 0)/1000) %>%
arrange(-positive_support)# Positively associated
element_predictions %>%
filter(mean >0) %>%
arrange(-positive_support) %>%
filter(positive_support>=0.9) %>%
tt()| trait | mean | p1 | p9 | positive_support | negative_support |
|---|---|---|---|---|---|
| D0205 | 0.012645450 | 0.0024775212 | 0.023274188 | 0.945 | 0.055 |
| D0208 | 0.010176614 | 0.0022117782 | 0.018696465 | 0.945 | 0.055 |
| D0906 | 0.003596117 | 0.0001275640 | 0.008020033 | 0.925 | 0.075 |
| D0504 | 0.004451800 | 0.0003726435 | 0.009522305 | 0.916 | 0.084 |
| B0103 | 0.008553518 | 0.0001228220 | 0.016976336 | 0.902 | 0.098 |
element_predictions %>%
filter(mean <0) %>%
arrange(-negative_support) %>%
filter(negative_support>=0.9) %>%
tt()| trait | mean | p1 | p9 | positive_support | negative_support |
|---|---|---|---|---|---|
| D0801 | -0.002090689 | -0.002438983 | -9.272219e-05 | 0.005 | 0.995 |
| D0802 | -0.002090689 | -0.002438983 | -9.272219e-05 | 0.005 | 0.995 |
| D0517 | -0.004532699 | -0.007986505 | -1.168789e-03 | 0.030 | 0.970 |
| B0302 | -0.005001966 | -0.010562544 | -5.506823e-04 | 0.039 | 0.961 |
| D0601 | -0.009173358 | -0.017653493 | -2.056762e-03 | 0.040 | 0.960 |
| B0310 | -0.012823144 | -0.023057077 | -2.492560e-03 | 0.045 | 0.955 |
| B0219 | -0.004220671 | -0.010020412 | -2.322877e-04 | 0.049 | 0.951 |
| D0603 | -0.001949497 | -0.003952858 | -3.128527e-04 | 0.049 | 0.951 |
| D0611 | -0.004163572 | -0.009897145 | -2.260342e-04 | 0.050 | 0.950 |
| D0903 | -0.004163572 | -0.009897145 | -2.260342e-04 | 0.050 | 0.950 |
| B0709 | -0.002067869 | -0.003601898 | -4.610807e-04 | 0.052 | 0.948 |
| D0610 | -0.002851369 | -0.004825160 | -6.045636e-04 | 0.061 | 0.939 |
| D0807 | -0.004248293 | -0.008791774 | -5.213497e-04 | 0.061 | 0.939 |
| B0804 | -0.016554792 | -0.030214130 | -2.413867e-03 | 0.066 | 0.934 |
| B0303 | -0.011651780 | -0.021956618 | -2.027232e-03 | 0.067 | 0.933 |
| D0817 | -0.004955047 | -0.010619045 | -4.375213e-04 | 0.067 | 0.933 |
| B0603 | -0.016917107 | -0.033606646 | -2.488392e-03 | 0.069 | 0.931 |
| B0401 | -0.012703245 | -0.027187239 | -1.024461e-03 | 0.075 | 0.925 |
| D0606 | -0.005849762 | -0.011667610 | -6.399018e-04 | 0.076 | 0.924 |
| B0214 | -0.020880218 | -0.038383544 | -2.819795e-03 | 0.078 | 0.922 |
| D0508 | -0.003423296 | -0.007959844 | -1.788522e-04 | 0.081 | 0.919 |
| D0908 | -0.015011644 | -0.027596991 | -1.822608e-03 | 0.084 | 0.916 |
| D0816 | -0.005769844 | -0.012208972 | -2.589436e-04 | 0.088 | 0.912 |
| B0601 | -0.009430120 | -0.018345796 | -4.765228e-04 | 0.089 | 0.911 |
| B0204 | -0.015628057 | -0.033743640 | -1.376524e-04 | 0.098 | 0.902 |
positive <- element_predictions %>%
filter(mean >0) %>%
arrange(mean) %>%
filter(positive_support>=0.9) %>%
select(-negative_support) %>%
rename(support=positive_support)
negative <- element_predictions %>%
filter(mean <0) %>%
arrange(mean) %>%
filter(negative_support>=0.9) %>%
select(-positive_support) %>%
rename(support=negative_support)
bind_rows(positive,negative) %>%
left_join(GIFT_db,by=join_by(trait==Code_element)) %>%
mutate(trait=factor(trait,levels=c(rev(positive$trait),rev(negative$trait)))) %>%
ggplot(aes(x=mean, y=fct_rev(trait), xmin=p1, xmax=p9, color=Function)) +
geom_point() +
geom_errorbar() +
xlim(c(-0.04,0.04)) +
geom_vline(xintercept=0) +
scale_color_manual(values = c("#debc14","#440526","#dc7c17","#172742","#debc14","#440526","#dc7c17","#172742","#357379","#6c7e2c","#d8dc69","#774d35","#db717d")) +
theme_minimal() +
labs(x="Regression coefficient",y="Functional trait")